Pivot Translation Research Articles

Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding

Linguistic steganography (LS) aims to embed secret information into a highly encoded text for covert communication. It can be roughly divided to two main categories, i.e., modification based LS (MLS) and generation based LS (GLS). MLS embeds secret data by slightly modifying a given text without impairing the meaning of the text, whereas GLS uses a well trained language model to directly generate a text carrying secret data. A common disadvantage for MLS methods is that the embedding payload is very small, whose return is well preserving the semantic quality of the text. In contrast, GLS enables the data hider to embed a large payload, which has to pay the high price of uncontrollable semantics. In this paper, we propose a novel LS method to modify a given text by pivoting it between two different languages and embed secret data using a semantic-aware information encoding strategy. Our purpose is to alter the expression of the given text, enabling a large payload to be embedded while keeping the semantic information unchanged. Experiments have shown that the proposed work not only achieves a large embedding payload, but also shows superior performance in maintaining the semantic consistency and resisting linguistic steganalysis.

The Mukokuseki Strategy and the Application of Pivot Translation in the Localization of Japanese Games

This article investigates the impact of using pivot language on the quality of game localization via a case study on the Japanese game Dark Souls 3. It first discusses the indirectness of the source text and the complexity of the target text in game localization by highlighting the “born translated” nature of the game narrative design. It then explicates the intricacy of having game audio voiced over in English only and including both direct and indirect translations in the localization workflow. It demonstrates the complication in evaluating localization quality from players’ perspectives and suggests that using English as a pivot language has certain advantages in ensuring multimodal cohesiveness in game localization. The rationale behind the localization approach is then explored through the lens of the mukokuseki strategy, which suggests that the application of pivot translation is driven by market globalization and, ultimately, the pursuit of economic gain.

Creativity in pivot audiovisual translation. Parasite subtitled and dubbed in Italian

ABSTRACT Creativity in pivot AVT is a burning issue, since the pivot text can be seen as imposing pre-existing patterns, which may limit the translator’s decision-making process and influence their creative output. To verify this, we examined the Italian subtitled and dubbed versions of the film Parasite (Bong Joon-ho, 2019), a well-known example of Korean audiovisual content transferred interlinguistically using English as a pivot language. The preliminary textual analysis of the data showed that both the Italian versions were also created using the pivot translation by Darcy Paquet. Being unable to retrieve the name of the Italian subtitler, we examined the Italian subtitles and found they are very close to the English pivot, often replicating some creative and controversial choices. For the Italian dubbing, we managed to interview the Italian dialogue writer (and dubbing director) and the translator. Their feedback on the translation process and the comparative analysis of the Korean source text, English subtitles and Italian dubbing demonstrated that the Italian dubbing team relied not only on the English subtitles but also on subtitles in other languages and the Korean script to create a text that often departs from the English pivot, and it is closer to the original.

Transfer and Triangulation Pivot Translation Approaches for Burmese Dialects

Parallel corpora for the languages of Myanmar (Beik, Burmese, Rakhine) are extremely scarce but a necessary requirement for machine translation R&D. Previous studies have proved that pivoting leads to better translation quality if the bridge language is closely related to the source and target language pair. The baseline study is conducted based on the three major approaches of machine translation; Weighted Finite State Transducer (WFST), Phrase-Based Statistical Machine Translation (PBSMT) and Deep Recurrent Neural Network (Deep-RNN). Based on the baseline results, this paper mainly investigated the pivot language technique for PBSMT with Burmese dialects. We employed two different pivot translation methods: transfer (sentence level) and triangulation (phrase level). We present the experimental results on Dawei-Beik, Beik-Dawei translations and Beik-Rakhine, Rakhine-Beik translation via Burmese. Both the transfer and triangulation approaches outperformed the baseline (direct translation), specifically for the Rakhine-Beik language pair. Moreover, the results of the average BiLingual Evaluation Understudy (BLEU), Character n-gram F-score (chrF), and Word Error Rate (WER) scores of the 10-fold cross-validation experiments proved that the triangulation pivot has significantly better acceleration than the transfer pivot. We plan to release the parallel corpora of Burmese dialects and present several avenues for further research.

Role of pivot translations in Asian film festivals in Catalonia

Pivot translations are very often used in film festivals, but have been granted little consideration from an academic viewpoint. This article analyses the role of pivot languages in audiovisual translation within the framework of Asian film festivals held in Catalonia. There are three aims of this paper: (i) to examine to what extent pivot translations are part of the translation process in films screened in such festivals, (ii) to determine the justifications for their use, and (iii) to analyse the effects of their use from a qualitative perspective. In order to do so, the answers from a questionnaire distributed among the most relevant agents in Asian film festivals in Catalonia will be analysed. Additionally, the Chinese film Old Stone by Johnny Ma that has been translated into and subtitled in Catalan through English as its pivot language, will be presented as a case study. Lay abstract The use of a third language or pivot translation is widespread in film festivals, although very few studies focus on this practice, which usually remains unnoticed by the average spectator. This article seeks to examine just how common this phenomenon is in film festivals and to analyse its impact with a case study, taking the Chinese film Old Stone by Johnny Ma and its translation into Catalan as an example. More precisely, the article aims to answer two questions regarding the use of pivot languages in audiovisual translation. Firstly, to what extent and for what exact purpose are pivot translations currently being used in Asian film festivals in Catalonia? Secondly, how does using a pivot language, in our case English, affect quality?

The quality of templates in subtitling. A survey on current market practices and changing subtitler competences

ABSTRACT The rapidly growing demand for subtitling on the global translation market has resulted in a new development which has revolutionised the way subtitles are created and distributed: the template. A template is a subtitle file containing a time-coded transcription of the dialogue to be later translated into multiple target languages. Loved by global subtitling companies and frowned upon by subtitlers, templates have become an inseparable part of modern subtitling workflows. The goal of our study is to examine this new development in terms of quality, its impact on the profession and the resulting changes in subtitler competences. With this goal in mind, we conducted an online survey which was completed by 344 professionals from 47 countries involved in the subtitling process with templates. We gathered data on the content of the templates, subtitling workflows, types of software, pivot translation, annotations, and language combinations. We found important differences in spotting skills between subtitlers depending on their experience and type of company they work for. Our results also show that the quality of templates currently available on the market is rather inadequate. We present suggestions for improvement based on the subtitlers’ views. The results may be used to inform current market practices.

Leveraging Additional Resources for Improving Statistical Machine Translation on Asian Low-Resource Languages

Phrase-based machine translation (MT) systems require large bilingual corpora for training. Nevertheless, such large bilingual corpora are unavailable for most language pairs in the world, causing a bottleneck for the development of MT. For the Asian language pairs—Japanese, Indonesian, Malay paired with Vietnamese—they are also not excluded from the case, in which there are no large bilingual corpora on these low-resource language pairs. Furthermore, although the languages are widely used in the world, there is no prior work on MT, which causes an issue for the development of MT on these languages. In this article, we conducted an empirical study of leveraging additional resources to improve MT for the Asian low-resource language pairs: translation from Japanese, Indonesian, and Malay to Vietnamese. We propose an innovative approach that lies in two strategies of building bilingual corpora from comparable data and phrase pivot translation on existing bilingual corpora of the languages paired with English. Bilingual corpora were built from Wikipedia bilingual titles to enhance bilingual data for the low-resource languages. Additionally, we introduced a combined model of the additional resources to create an effective solution to improve MT on the Asian low-resource languages. Experimental results show the effectiveness of our systems with the improvement of +2 to +7 BLEU points. This work contributes to the development of MT on low-resource languages, especially opening a promising direction for the progress of MT on the Asian language pairs.

Syntactic Matching Methods in Pivot Translation

The pivot translation is useful method for translating between languages that contain little or no parallel data by utilizing equivalents in an intermediate language such as English. Commonly, phrase-based or tree-based pivot translation methods merge source–pivot and pivot–target translation models into a source–target model. This tactic is known as triangulation. However, the combination is based on the surface forms of constituent words, and it often produces incorrect source–target phrase pairs because of interlingual differences and semantic ambiguities in the pivot language. The translation accuracy is thus degraded. This paper proposes a triangulation approach that utilizes syntactic subtrees in the pivot language to avoid incorrect phrase combinations by distinguishing pivot language words by their syntactic roles. The results of the experiments conducted on the United Nations Parallel Corpus demonstrate that the proposed method is superior to other pivot translation approaches in all tested combinations of languages.

中間言語情報を記憶するピボット翻訳手法

Pivot translation allows for translation of language pairs with little or no parallel data by introducing a third language for which data exists. In particular, the triangulation method, which translates by combining source-pivot and pivot-target translation models into a source-target model, is known for its high translation accuracy. However, in the conventional triangulation method, information of pivot phrases is forgotten and not used in the translation process. In this paper, we propose a novel approach torememberthe pivot phrases in the triangulation stage, and use a pivot language model as an additional information source at translation time. Experimental results on the Europarl corpus showed gains of 0.4-1.2 BLEU points in all tested combinations of languages 1 .

Compliant bipedal model with the center of pressure excursion associated with oscillatory behavior of the center of mass reproduces the human gait dynamics

Although the compliant bipedal model could reproduce qualitative ground reaction force (GRF) of human walking, the model with a fixed pivot showed overestimations in stance leg rotation and the ratio of horizontal to vertical GRF. The human walking data showed a continuous forward progression of the center of pressure (CoP) during the stance phase and the suspension of the CoP near the forefoot before the onset of step transition. To better describe human gait dynamics with a minimal expense of model complexity, we proposed a compliant bipedal model with the accelerated pivot which associated the CoP excursion with the oscillatory behavior of the center of mass (CoM) with the existing simulation parameter and leg stiffness. Owing to the pivot acceleration defined to emulate human CoP profile, the arrival of the CoP at the limit of the stance foot over the single stance duration initiated the step-to-step transition. The proposed model showed an improved match of walking data. As the forward motion of CoM during single stance was partly accounted by forward pivot translation, the previously overestimated rotation of the stance leg was reduced and the corresponding horizontal GRF became closer to human data. The walking solutions of the model ranged over higher speed ranges (~1.7m/s) than those of the fixed pivoted compliant bipedal model (~1.5m/s) and exhibited other gait parameters, such as touchdown angle, step length and step frequency, comparable to the experimental observations. The good matches between the model and experimental GRF data imply that the continuous pivot acceleration associated with CoM oscillatory behavior could serve as a useful framework of bipedal model.

How to Choose the Best Pivot Language for Automatic Translation of Low-Resource Languages

Recent research on multilingual statistical machine translation focuses on the usage of pivot languages in order to overcome language resource limitations for certain language pairs. Due to the richness of available language resources, English is, in general, the pivot language of choice. However, factors like language relatedness can also effect the choice of the pivot language for a given language pair, especially for Asian languages, where language resources are currently quite limited. In this article, we provide new insights into what factors make a pivot language effective and investigate the impact of these factors on the overall pivot translation performance for translation between 22 Indo-European and Asian languages. Experimental results using state-of-the-art statistical machine translation techniques revealed that the translation quality of 54.8% of the language pairs improved when a non-English pivot language was chosen. Moreover, 81.0% of system performance variations can be explained by a combination of factors such as language family, vocabulary, sentence length, language perplexity, translation model entropy, reordering, monotonicity, and engine performance.